Review on Interpretable Machine Learning in Smart Grid

Abstract

In recent years, machine learning, especially deep learning, has developed rapidly and has shown remarkable performance in many tasks of the smart grid field. The representation ability of machine learning algorithms is greatly improved, but with the increase of model complexity, the interpretability of machine learning algorithms is worse. The smart grid is a critical infrastructure area, so machine learning models involving it must be interpretable in order to increase user trust and improve system reliability. Unfortunately, the black-box nature of most machine learning models remains unresolved, and many decisions of intelligent systems still lack explanation. In this paper, we elaborate on the definition, motivations, properties, and classification of interpretability. In addition, we review the relevant literature addressing interpretability for smart grid applications. Finally, we discuss the future research directions of interpretable machine learning in the smart grid.

A Review on the Evaluation of Feature Selection Using Machine Learning for Cyber-Attack Detection in Smart Grid

“…ACO has been utilized in machine learning to efficiently find subsets of features, hence improving the interpretability of models [112]. Evolutionary computing techniques are crucial in optimizing feature subsets, leading to improved model performance and interpretability in diverse applications such as smart grids and machine learning [113]. Their use demonstrates their efficacy in addressing feature selection issues in intricate datasets [114].…”

A Review of Machine Learning Approaches in Synchrophasor Technology

“…As a solution for this ML technologies are adopted and have attracted a lot of attention in recent years. Numerous studies are reported in the field of ML-based technologies in PS monitoring, protection and stability assessments which are commonly observed in PS generation, transmission and distribution addressed in [67], [68], [69]. As illustrated in Fig.…”

Energy Efficiency Evaluation and Forecasting of the Sussex Ports to Address Climate Change Concerns: a Data-driven Decision Model

“…For the end user side, prediction of energy management factors and behavior price provisioning is an important challenge that machine learning algorithms can detect and help in overcoming through developing appropriate solutions for this problem (Mirshafiee et al, 2023). Some recent review papers, like Rangel-Martinez et al ( 2021) and Zhang et al (2018), have categorized renewable energy management strategies according to existing aspects of prediction approaches such as machine learning and deep learning methods in power communication systems (Xu et al, 2022)…”